Advanced search
1 file | 1.94 MB Add to list

Learning Local Image Descriptors with Autoencoders

Author
Organization
Abstract
In this paper, we propose an efficient method for learning local image descriptors with convolutional autoencoders. We design an autoencoder architecture that yields computationally efficient extraction of patch descriptors through an intermediate image representation. The proposed approach yields significant savings in memory and processing time compared to a reference autoencoder-based patch descriptor. The results demonstrate improved robustness to noise and missing data.
Keywords
Local image descriptors, Autoencoders, Unsupervised deep learning

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.94 MB

Citation

Please use this url to cite or link to this publication:

MLA
Žižakić, Nina, et al. “Learning Local Image Descriptors with Autoencoders.” Image Processing and Communications, edited by Michał Choraś and Ryszard S. Choraś, vol. 1062, Springer, 2019, pp. 214–21.
APA
Žižakić, N., Ito, I., & Pizurica, A. (2019). Learning Local Image Descriptors with Autoencoders. In M. Choraś & R. S. Choraś (Eds.), Image Processing and Communications (Vol. 1062, pp. 214–221). Cham: Springer.
Chicago author-date
Žižakić, Nina, Izumi Ito, and Aleksandra Pizurica. 2019. “Learning Local Image Descriptors with Autoencoders.” In Image Processing and Communications, edited by Michał Choraś and Ryszard S. Choraś, 1062:214–21. Cham: Springer.
Chicago author-date (all authors)
Žižakić, Nina, Izumi Ito, and Aleksandra Pizurica. 2019. “Learning Local Image Descriptors with Autoencoders.” In Image Processing and Communications, ed by. Michał Choraś and Ryszard S. Choraś, 1062:214–221. Cham: Springer.
Vancouver
1.
Žižakić N, Ito I, Pizurica A. Learning Local Image Descriptors with Autoencoders. In: Choraś M, Choraś RS, editors. Image Processing and Communications. Cham: Springer; 2019. p. 214–21.
IEEE
[1]
N. Žižakić, I. Ito, and A. Pizurica, “Learning Local Image Descriptors with Autoencoders,” in Image Processing and Communications, Bydgoszcz, Poland, 2019, vol. 1062, pp. 214–221.
@inproceedings{8628719,
  abstract     = {In this paper, we propose an efficient method for learning local image descriptors with convolutional autoencoders. We design an autoencoder architecture that yields computationally efficient extraction of patch descriptors through an intermediate image representation. The proposed approach yields significant savings in memory and processing time compared to a reference autoencoder-based patch descriptor. The results demonstrate improved robustness to noise and missing data.},
  author       = {Žižakić, Nina and Ito, Izumi and Pizurica, Aleksandra},
  booktitle    = {Image Processing and Communications},
  editor       = {Choraś, Michał and Choraś, Ryszard S.},
  isbn         = {9783030312534},
  issn         = {2194-5357},
  keywords     = {Local image descriptors,Autoencoders,Unsupervised deep learning},
  language     = {eng},
  location     = {Bydgoszcz, Poland},
  pages        = {214--221},
  publisher    = {Springer},
  title        = {Learning Local Image Descriptors with Autoencoders},
  url          = {http://dx.doi.org/10.1007/978-3-030-31254-1_26},
  volume       = {1062},
  year         = {2019},
}

Altmetric
View in Altmetric